A CREAM model optimization method based on fatigue testing experiments and machine learning techniques for maritime transportation applications

Maritime transportation has a crucial position in world trade, but maritime transportation accidents still occur frequently. To assess human errors in maritime transportation more accurately by CREAM and thus improve the reliability of maritime transportation, the study is the first to obtain the quantitative effects of different anti-fatigue capability groups on task performance in the field of maritime transportation by combining fatigue test experiments with machine learning. First, a dataset reflecting the fatigue changes of participants in maritime transportation tasks is constructed by 91 subjects participating in fatigue test experiments. Second, anti-fatigue capability classifications were performed by machine learning algorithms based on Density Peak Clustering Algorithm and fitness. Again, the failure probability correction coefficients of different anti-fatigue capability classes are obtained based on the classification results. Finally, the proposed model optimization method is experimentally verified. The results show that the optimized model is more accurate for the estimation of human-caused errors in maritime transportation. The proposed model effectively improves the inaccuracy of the traditional CREAM due to the lack of attention to individual physiological differences in the reliability assessment. •Changes in subject fatigue and task performance during a continuous maritime transportation task were explored through ergonomics experiments.•Machine learning algorithms for unbalanced dataset classification was applied to classify experimental datasets.•Human Inherent Factors (HIFs) were integrated into CREAM to reflect physiological differences between individuals.